Data-Driven Condition Monitoring of Fixed-Turnout Frogs Using Standard Track Recording Car Measurements
Source abstract
Abstract
Turnouts are critical components of railway infrastructure, ensuring operational flexibility but also representing a significant share of track maintenance costs. The frog, as the most vulnerable part of a turnout, is subject to severe wear and degradation, requiring frequent inspection and maintenance. Traditional manual inspection methods are costly, labour-intensive, and susceptible to subjectivity. This study explores a data-driven approach to condition monitoring of fixed-turnout frogs using standard track recording car measurements. By leveraging over 20 years of longitudinal level and rail surface signal data from the Austrian track-recording measurement car, we assess the feasibility of using existing measurement data for predictive maintenance. Six complementary approaches are proposed to evaluate frog condition, including track geometry assessment, ballast condition analysis, rail surface irregularity detection, and axle box acceleration-based monitoring. Results indicate that data-driven monitoring enhances maintenance decision-making by identifying deterioration trends, reducing reliance on manual inspections, and enabling predictive interventions. The integration of standardised measurement data with advanced analytical models offers a cost-effective and scalable solution for turnout maintenance.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Hydraulic and Pneumatic Systems · Fault Detection and Control Systems · Transport Systems and Technology
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute of Railway Engineering and Transport Economics, Graz University of Technology, 8010 Graz, Austria
Funding
The Austrian Research Promotion Agency
References (39)
Show source-provided references
1. A Data Driven Degradation-Based Model for the Maintenance of Turnouts: A Case Study10.1016/j.ifacol.2015.09.650 ↗
2. (2025, May 06). Wheel/Rail Impacts at a Railway Turnout Crossing. Available online: https://journals.sagepub.com/doi/epdf/10.1243/0954409981530733.
3. A Review of Loading Conditions for Railway Track Structures Due to Train and Track Vertical Interaction10.1002/stc.227 ↗
4. A Digital Filter-Based Approach to the Remote Condition Monitoring of Railway Turnouts10.1016/j.ress.2006.02.011 ↗
5. Fellinger, M. (2020). Sustainable Asset Management for Turnouts—From Measurement Data Analysis to Behaviour and Maintenance Prediction, Graz University of Technology.
6. Hamarat, M., Apaelias, M., Kaewunruen, S., and Silvast, M. (2019, January 10–13). Dynamic Analysis of a Railway Turnout System Under Moving Train Loads. Proceedings of the ACOUSTICS 2019, Cape Schancku, VA, Australia.
7. Dynamic Interaction between Train and Railway Turnout: Full-Scale Field Test and Validation of Simulation Models10.1080/00423110801993144 ↗
8. Geometry and Stiffness Optimization for Switches and Crossings, and Simulation of Material Degradation10.1243/09544097JRRT348 ↗
9. Ossberger, U., Eck, S., and Stocker, E. (2015, January 21–24). Performance of Different Materials in a Frog of a Turnout. Proceedings of the IHHA, Perth, WA, Australia.
10. Ossberger, U., Pletz, M., Eck, S., and Daves, W. (2013, January 19–23). Validation of a Finite Element Crossing Model Using Measurements at an Instrumented Turnout. Proceedings of the 23rd International Symposium on Dynamics of Vehicles on Roads and Tracks, Qingdao, China.
11. Loidolt, M. (2024). Integration of Short-Wave Effects into Asset Management of Railway Infrastructure: An Alternative Perspective on the Quality Behaviour of Tracks, Graz University of Technology.
12. Wilfling, P.A. (2018, January 17–19). From Manual Inspection to Permanent Monitoring of Turnouts. Proceedings of the 5th International Conference on Road and Rail Infrastructure, Zadar, Croatia.10.5592/CO/CETRA.2018.886 ↗
13. (2017). Railway Applications—Track—Track Geometry Quality. Part 5: Geometric Quality Levels—Plain Line, Switches and Crossings. (Standard No. EN 13848-5).
14. Condition-based Maintenance: Tools and Decision Making10.1108/13552519510096350 ↗
15. Data-Driven Optimization of Railway Maintenance for Track Geometry10.1016/j.trc.2018.02.019 ↗
16. Statistical Model of Railway’s Turnout Based on Train Induced Vibrations10.1016/j.ifacol.2018.09.570 ↗
17. Unsupervised domain adaptation method for bearing fault diagnosis assisted by twin data under extreme sample scarcity10.1016/j.ymssp.2025.113359 ↗
18. Vale, C., and Simões, M.L. (2022). Prediction of Railway Track Condition for Preventive Maintenance by Using a Data-Driven Approach. Infrastructures, 7.10.3390/infrastructures7030034 ↗
19. Degradation Prediction of Rail Tracks: A Review of the Existing Literature10.2174/1874447801812010088 ↗
20. Improvement of Railway Ballast Maintenance Approach, Incorporating Ballast Geometry and Fouling Conditions10.1016/j.jappgeo.2018.02.020 ↗
21. Track Geometry Degradation and Maintenance Modelling: A Review10.1177/0954409716657849 ↗
22. Ballast Condition Monitoring for Turnouts Using Power Spectral Density10.1061/JTEPBS.0000433 ↗
23. Loidolt, M., and Marschnig, S. (2022). Evaluating Short-Wave Effects in Railway Track Using the Rail Surface Signal. Appl. Sci., 12.10.3390/app12052529 ↗
24. Loidolt, M., Marschnig, S., and Berghold, A. (2023). Track Geometry Quality Assessments for Turnouts. Transp. Eng., 12.10.1016/j.treng.2023.100170 ↗
25. A Visual Inspection System for Rail Detection & Tracking in Real Time Railway Maintenance10.2174/1874110X00802010057 ↗
26. Railway Turnout Defect Detection Using Image Processing
27. (2019). Railway Applications—Track—Track Geometry Quality—Part 1: Characterization of Track Geometry 2019 (Standard No. EN 13848-1).
28. Weld battering of thermite welds and flash butt Welds Based on Statistical Evaluations10.1016/j.engfailanal.2025.109457 ↗
29. The Effect of Track and Vehicle Parameters on Wheelrail Vertical Dynamic Forces
30. (2025, September 16). D2.2.6 Report on Hybrid Approach Algorithm, D2.2.7 Report on Prediction Algorithms, D2.2.8 Report on Deployment and Demonstration. Available online: https://www.rail4future.com/en/insights-rd/r4f-area2.
31. Bezin, Y., Grossoni, I., and Neves, S. (2015, January 17–21). Impact of Wheel Shape on the Vertical Damage of Cast Crossing Panels in Turnouts. Proceedings of the Dynamics of Vehicles on Roads and Tracks—Proceedings of the 24th Symposium of the International Association for Vehicle System Dynamics, IAVSD 2015, Graz, Austria.
32. Rupp, M., Lorenzen, S., Huebler, C., Wolter, K., Grunert, G., and Stein, R. (2024). Indirect Continuous Monitoring of Bridge Transitions Using the CTM 2.0. Bridge Maintenance, Safety, Management, Digitalization and Sustainability, CRC Press.10.1201/9781003483755-203 ↗
33. A Simple Approach to Integration of Acceleration Data for Dynamic Soil-Structure Interaction Analysis10.1016/j.soildyn.2005.12.011 ↗
34. Insights towards Condition Monitoring of Fixed Railway Crossings10.1016/j.prostr.2017.07.007 ↗
35. Review of Wheel-Rail Forces Measuring Technology for Railway Vehicles10.1177/16878132231158991 ↗
36. Loidolt, M., Marschnig, S., Bürgler, M., Berghold, A., Dornig, P., and Ossberger, U. (2023). Quality Behaviour of Turnouts: Comparison, Problem Specification and Recommendation of Measures. Appl. Sci., 13.10.3390/app131910665 ↗
37. Neuhold, J. (2020). Automated Tamping Scheduling for Optimising Life Cycle Costs, Graz University of Technology.
38. Offenbacher, S. (2025). Effective Railway Track Tamping: Evaluating Short-Term and Long-Term Impacts on Track Geometry and Monitoring Ballast Condition, Technischer Universität Graz.
39. Evaluating the Applicability of Multi-Sensor Equipped Tamping Machines for Ballast Condition Monitoring10.1016/j.measurement.2020.108881 ↗